SKILLEMALL.ai
RU Sign in

BF bird-dm

An add-on to the Bird skill that lets your agent check its X/Twitter DM inbox. Use when the user asks to check DMs, read Twitter direct messages, list DM conversations, or monitor their X inbox.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 8 files body ≈ 263 tokens Open the sourcegithub.com↗ analyzed 33 h ago

An add-on to the Bird skill that lets your agent check its X/Twitter DM inbox.

As a process F 32/100 · Will not run — weak spots: steps, result and completion, inputs and preconditions

ReferenceAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
76
Quality 40%
81
Run on models
none yet
Process rating
F
32/100
Will not run
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 7

  • high Exfiltration intent-browser-credential-store README.md:57
    Accesses a browser credential / cookie store
    const { cookies } = await resolveCredentials({ cookieSources: ['chrome'] });
Medium and low: 6
  • low Secrets in code secret-high-entropy-token package-lock.json:30
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-GZMB+a0mO…4cw+w1WV…UED+1X8a…sJi+8mgpw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:200
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…HK5+NE/tvnRLbIqUWa+0E9N4WNMjmp/kXXP…R8w==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:421
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…78O/B3Kkh+nKABUF++bvJv…56W+C8F9…X6m+IktJnIb1Jjg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:498
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…7sL+iGzu…aOw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:508
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…0YH+uCmB…OWQ==",
    detector
  • low Secrets in code secret-high-entropy-token src/dm-client.ts:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const BEARER_TOKEN = 'AAAA…uTs%3D1Z…TnA';
    quoted

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 32/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (bird-dm) differs from the folder (bird-dms)
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Execution cost. Instruction body is 263 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 194: enough signal without eating the budget
  • +4Structure: 5 headings
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.